Adjusts the map of (var, grad) with Lp regularization, where p=1.0 or 2.0. Args: var_grads: a `.NestedMap` or list of (variable, gradient). lp_regularizer_weight: Lp regularization weight. p: For now we support 1.0 or 2.0. Returns: A tuple (lp_loss, var_grads). - lp_loss:
(var_grads, lp_regularizer_weight, p=2.0)
source not stored for this graph (policy: none)
nothing calls this directly
no test coverage detected
searching dependent graphs…